Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of progress, advancement, or development

    oai_token-act-pair · gpt-3.5-turbo

    references to progress or advancement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ters
    -0.78
    ============
    -0.73
    DOWN
    -0.72
    sey
    -0.72
     recoil
    -0.70
    say
    -0.69
    tics
    -0.68
    ãĥ¼ãĥ
    -0.67
    kered
    -0.67
    SIZE
    -0.64
    POSITIVE LOGITS
    heit
    0.87
    uve
    0.79
     directives
    0.79
    ments
    0.79
     furthe
    0.75
     towards
    0.69
    anced
    0.67
     Centauri
    0.66
     toward
    0.66
     beyond
    0.66
    Act Density 0.054%

    No Known Activations